agentforce-d360-analyze
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the Salesforce (
sf) CLI to perform administrative and data-fetching tasks. - It executes
sf org displayto retrieve instance metadata. - It executes
sf org auth show-access-tokento obtain temporary credentials for API access. - It executes
sf config get target-orgto determine the environment context. - Security controls: All command outputs are passed through a redaction function (
dc.py: _redact_text) that scrubs bearer tokens and access tokens using regex before surfacing errors or logging output. - [EXTERNAL_DOWNLOADS]: The skill performs network requests to interact with Salesforce Data Cloud APIs.
- It uses
urllib.requestto POST SQL queries to Data Cloud endpoints (e.g.,https://<instance>/services/data/v66.0/ssot/query). - These requests are authenticated using tokens obtained via the
sfCLI. - The domains are established via the user's authenticated Salesforce CLI aliases, belonging to the vendor (Salesforce).
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests and renders untrusted session data.
- Ingestion points:
fetch_dc.pyretrieves session transcripts, user utterances, and LLM generations from Data Cloud and saves them to JSON artifacts. - Boundary markers:
render_dc.pyrenders this data into a markdown summary using structured headers, blockquotes for messages, and fenced code blocks for raw prompt/completion text. - Capability inventory: The skill can execute shell commands via
sfand perform network requests to Salesforce APIs. If an agent follows instructions embedded in a session summary (e.g., 'Delete all files'), it could abuse these capabilities. - Sanitization: The skill implements display caps (64 KB for prompts), HTML unescaping for readability, and robust path validation via
fs_guard.pyto prevent path traversal when saving or reading artifacts.
Audit Metadata